Tulpa
Tulpa is an MCP server that lets AI agents search chat history and Bilibili videos for people who work across QQ, WeChat, and Bilibili.
What it is good for
- Finding files and messages in old QQ or WeChat chat history
- Searching Bilibili videos and reading their subtitles and comments
- Letting an AI agent take part in a QQ group chat with a custom persona
At a glance
- Who it is for
- Setup
- Install a desktop app or browser extension
Level 3 of 5. Download and install it like any other app or extension.
- Cost
- Free and open source
- Type
- MCP server or connector
- Tasks
- Works with
- Codex, Claude Code, DeepSeek Harness, Antigravity, WorkBuddy, OneBot
Momentum
- Rank this week
- Not ranked (last #99, week 41, 2026)
- Best rank
- #99 week 41, 2026
- GitHub stars
- 503
GitHub numbers as of Nov 2, 2026. Updated weekly.
Ranking history
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is Tulpa free?
- Yes. It is free and open source (MIT license).
- Do I need to know how to code to use Tulpa?
- No. Download and install it like any other app or extension.
- What does Tulpa work with?
- According to its own documentation, it works with Codex, Claude Code, DeepSeek Harness, Antigravity, WorkBuddy, and OneBot.
- What is Tulpa good for?
- Finding files and messages in old QQ or WeChat chat history, searching Bilibili videos and reading their subtitles and comments, and letting an AI agent take part in a QQ group chat with a custom persona.
Similar agents to Tulpa
- ghidra-mcp
ghidra-mcp is an MCP server that lets AI tools analyze and document binaries in Ghidra for reverse engineers.
- webclaw
webclaw is a web extraction tool that turns websites into clean markdown or JSON for AI agents and apps, usable from a terminal, MCP, or API.
- Firecrawl
Firecrawl is an API that searches the web and pulls clean page content for AI agents and apps.
- Scrapling
Scrapling is a Python web scraping framework that collects data from websites, including JavaScript-heavy and bot-protected ones, for developers.
- PageIndex
PageIndex is a Python library that helps an LLM find answers in long professional documents by reasoning over a document tree instead of vector search.
- book-to-skill
book-to-skill is a skill that turns a technical book PDF into a structured skill your AI agent can search chapter by chapter, for people who want to reuse a book's content while they work.